Upload 8 files

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: Qwen/Qwen3-4B-Instruct-2507
 datasets:
-- u-10bei/structured_data_with_cot_dataset_512_v4
+- u-10bei/structured_data_with_cot_dataset_512_v5
 language:
 - en
 license: apache-2.0
@@ -36,7 +36,7 @@ while intermediate reasoning (Chain-of-Thought) is masked.
 - Max sequence length: 2048
 - Epochs: 2
 - Learning rate: 2e-05
-- LoRA: r=64, alpha=128
+- LoRA: r=32, alpha=64
 
 ## Usage
 
@@ -59,7 +59,7 @@ model = PeftModel.from_pretrained(model, adapter)
 
 ## Sources & Terms (IMPORTANT)
 
-Training data: u-10bei/structured_data_with_cot_dataset_512_v4
+Training data: u-10bei/structured_data_with_cot_dataset_512_v5
 
 Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
 Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.

adapter_config.json

@@ -20,16 +20,16 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 64,
   "lora_bias": false,
-  "lora_dropout": 0.0,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 64,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab452917b9676ed68820c5af6ba4fb9ea18da7c160985061f2e7f7804ccc7ca
-size 528550256
+oid sha256:b691675d975607c342b28d8000efb8351664544a04ed80643eba37ea51c891cd
+size 264308896